Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
A Fire suppression monitoring system for smart building
Full text linkA fire suppression system (FSS) monitoring system is a system to monitor the FSS devices’ status since FSS is a critical system to respond to fire disasters. The monitoring system collects data on important parameters which are water pressure, main power status, and backup power status. The FSS monitoring system is built with an IoT capability where data are collected from the FSS module and sent to the IoT platform through Wi-Fi based Internet connection. Then the data will be displayed in a dashboard application. A QoS assessment framework is referred to and performed to check the performance of the FSS monitoring system, namely the TIPHON framework, which consists of five parameters: bandwidth, throughput, packet loss, delay, and jitter. The overall score for the FSS system using the TIPHON standard is 3.2 or categorized as “good”.Sistem monitoring fire suppression system (FSS) adalah sistem untuk memantau status perangkat FSS karena FSS merupakan sistem kritis untuk merespon bencana kebakaran. Sistem pemantauan mengumpulkan data tentang parameter penting yaitu tekanan air, status daya utama, dan status daya cadangan. Sistem monitoring FSS dibangun dengan kemampuan IoT dimana data dikumpulkan dari modul FSS dan dikirim ke platform IoT melalui koneksi internet berbasis Wi-Fi. Kemudian data tersebut akan ditampilkan di aplikasi dashboard. Kerangka penilaian QoS dirujuk dan dilakukan untuk memeriksa kinerja sistem pemantauan FSS, yaitu kerangka kerja TIPHON, yang terdiri dari lima parameter: bandwidth, throughput, packet loss, delay, dan jitter. Skor keseluruhan untuk sistem FSS yang menggunakan standar TIPHON adalah 3,2 atau dikategorikan “baik”
Implementation of multiple linear regression to estimate profit on sales of screen printing equipment
No full textTraditional marketing strategies are no longer practical to implement because the process requires more costs and time to disseminate information which is much longer. Data Mining is a science that discusses knowledge from previous data to estimate the amount of production in the future. Data mining is a term used to find hidden knowledge in databases. “Data mining is a semi-automatic process using statistical, mathematical, artificial intelligence, and machine learning techniques to extract and identify valuable and helpful information in large databases. It is necessary to solve the problem by using one of the five methods in the field of Data Mining, namely the Multiple Linear Regression method, where this method will analyze the variables that have an influence and can make estimates. Multiple Linear Regression Is a method that can be used to analyze data and obtain meaningful conclusions about a relationship between one variable and another. This relationship is generally expressed by a mathematical equation expressing the relationship between the independent and dependent variables in the form of a simple equatio
Identifying customer preferences on two competitive startupproducts: An analysis of sentiment expressions and textmining from Twitter data
No full textStartups have great potential to grow and scale up their business quickly; moreover, they have an essential role in the growth of the country and the global economy. However, with the high risk of failure, startup success needs to be supported and concerned. The success of startups depends on market needs and expectations, which are currently highly uncertain, dynamic, and chaotic. Thus, it is necessary to identify and monitor customer preferences for startup products/services. This research identifies the customer preferences of two competitive food delivery startups that have been successful, namely Go Food and Grab Food. With increasing customer opinions on social media, Twitter data can be used to explore customer needs and preferences. However, social media data like Twitter tend to be unstructured, informal, and noisy, so data mining mechanisms are needed. Using sentiment analysis and text mining methods, this study explores and compares customer preferences for successful startup products, which has yet to be done in previous studies. The sentiment analysis results show the dominance of positive customer opinions and expressions of the products/services offered. Furthermore, customer product aspects reviewed positively and negatively by customers were analyzed more deeply using text mining to find the strength and weaknesses of these two businesses. The method and analysis of this paper help monitor customer opinions in real-time, both related to their satisfaction and complaints. Finally, the research results have been validated by comparing sentiment analysis classifications using machine learning and manual analysis by experts, which show an accuracy of 85% and 86% in Go Food and Grab Food reviews
Performance comparison of cache replacement algorithms onvarious internet traffic
Full text linkInternet users tend to skip and look for alternative websites if they have slow response times. For cloud network managers, implementing a caching strategy on the edge network can help lighten the workload of databases and application servers. The caching strategy is carried out by storing frequently accessed data objects in cache memory. Through this strategy, the speed of access to the same data becomes faster. Cache replacement is the main mechanism of the caching strategy. There are seven cache replacement algorithms with good performance that can be used, namely LRU, LFU, LFUDA, GDS, GDSF, SIZE, and FIFO. The algorithm is developed uniquely according to the internet traffic patterns encountered. Therefore, a particular cache replacement algorithm cannot be superior to other algorithms. This paper presents a performance comparison simulation of the seven cache replacement algorithms on various internet traffic extracted from the public IRcache dataset. The results of this study indicate that the hit ratio performance is strongly influenced by cache size, cacheable and unique requests. The smaller the unique request that occurs, the greater the hit ratio performance obtained. The LRU algorithm shows an excellent hit ratio performance to perform cache replacement work under normal internet conditions. However, when the access impulse phenomenon occurs, the GDSF algorithm is superior in obtaining hit ratios with limited cache memory capacity. The simulation results show that GDSF reaches a 50.75% hit ratio while LRU is only 49.17% when access anomalies occur.Para pengguna internet cenderung melewati dan mencari alternatif website jika memiliki waktu respons yang lambat. Bagi para pengelola jaringan cloud, implementasi caching strategy pada edge network dapat membantu meringankan beban kerja database maupun application server. Strategi caching dilakukan dengan cara menyimpan objek data yang sering diakses pada suatu cache memory. Melalui strategi ini, kecepatan akses data yang sama menjadi lebih cepat. Cache replacement adalah mekanisme utama dari strategi caching. Ada tujuh algoritme cache replacement dengan kinerja baik yang dapat digunakan yaitu Least Recently Used (LRU), Least Frequently Used (LFU), Least Recently Used-Dinamic Aging (LFUDA), Greedy-Dual Size (GDS), Greedy-Dual Size Frequency (GDSF), SIZE, dan First in First out (FIFO). Algoritme tersebut dikembangkan secara unik sesuai dengan pola trafik internet yang dihadapi. Oleh karena itu suatu algortime cache replacement tertentu tidak dapat dikatakan unggul dari algoritme lainnya. Paper ini menyajikan simulasi perbandingan kinerja tujuh algoritme cache replacement tersebut pada various internet traffic yang diekstrak dari public dataset IRcache. Hasil penelitian ini menunjukan bahwa kinerja hit ratio sangat dipengaruhi oleh cache size, cacheable dan unique request. Semakin kecil unique request yang terjadi, semakin besar kinerja hit ratio yang diperoleh. Algoritme LRU menunjukkan kinerja hit ratio yang sangat baik untuk melakukan pekerjaan cache replacement pada kondisi internet yang normal. Namun ketika terjadi fenomena anomali, seperti access impulse, algoritme GDSF lebih unggul dalam perolehan hit ratio pada kapasitas cache memory yang terbatas. Hasil simulasi menunjukkan algoritme GDSF mampu mencapai 50,75% hit ratio sedangkan LRU hanya mampu mencapainya 49,17% saat terjadi anomali akses
A Proposal for Regulation of The Spectrum Usage Fee in 5G Private Network
No full textThis study evaluates the types of regulation models for The Indonesia Spectrum Usage Fee—the so-called Biaya Hak Pengguna (BHP) Frequency in 5G private network technology that are most suitable for implementation in Indonesia by implementing the Fuzzy Analytical Hierarchy Process (F-AHP) method. This method accommodates the opinions of telecommunications experts from mobile network operators (MNOs), regulators, vertical industries, and telecommunications consultants through a series of scientific steps to produce weights for each type of alternative solution offered. The results obtained show that the proposed model most suitable for implementation in Indonesia, taking into account the given criteria, is the one that uses unlicensed 5G frequencies. This model involves vertical industries not using licensed frequencies established by the government but rather choosing to use unlicensed frequencies to develop 5G technology for their own use. The implementation of this model is expected to encourage the optimization of regulation for Spectrum Usage Fee in 5G private network technology owned by the government, providing opportunities for vertical industries to develop 5G technology on private networks independently without relying on existing MNOs. This can stimulate innovation and technological progress in Indonesia to support Industry 4.0
Prediksi Saham Multi-Industri Menggunakan Deep Transfer Learning
No full textAfter the Covid-19 pandemic, the number of investors in Indonesia has proliferated. In managing a good stock portfolio, investors need the right strategy too. One approach that can be applied is to predict stock movements by considering the company's industrial sector. This paper proposed a new framework for applying deep transfer learning for stock forecasting in multi-industry. The model used in the framework is a combined algorithm between Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM). The author built the pre-trained model using Indeks Harga Saham Gabungan (IHSG) and transferred it to predict Indonesia's stock indexes based on industry classification (IDX-IC) as the measurer of stock movement in multiple industries. The outcomes reveal that this framework produces good model predictions and can be used to help analyze the evaluation of the pre-trained model to conduct transfer learning stock prediction in different industries efficiently. The model built using the IHSG indexes can predict stock prices best in the energy, technology, and industrial sectors
Room cleaning robot movement using A* algorithm and imperfect maze
Full text linkCleanliness is a mandatory requirement to help prevent virus spread. The cleaning process can be done automatically by humans or robotic devices. If a robot does this process, it is a must that the robot is able to explore the room autonomously. The robot movement in room tracking should reach all points without obstructions and return to its initial position. This study simulated the movement of a room explorer robot using the imperfect maze method, as well as searching a room that has not been explored using the A* algorithm. The A* algorithm was also used to find the shortest path to reach the initial place of the robot when the room exploration was completed. The results of the simulation showed that the imperfect maze could be used to explore the room well, and A* algorithm is quite optimal to be used for searching both the unexplored room and the path to return to its initial position
 
Application of the k-means clustering method and simple linear regression to new student admissions as a promotion method
Full text linkAt private label universities in Indonesia, new students are still the main thing in terms of achieving university operational income. This study intends to group the data of ITTelkom Surabaya students by utilizing the data mining process using the k-means clustering method, then the results of the clustering are forecasted using simple linear regression to be able to predict the achievement of new students as the effect variable and year as the causative variable. The results of this study consist of 5 variables, namely student province, student study program, income of student parents, student parent work and student ethnicity, each of which consists of 4 clusters, then each cluster is predicted for achievement 3 the coming year 2022,2023,2024. It can be concluded that the highest combination of student/parent student profiles was obtained from East Java province, information systems study program, parents' income of 5-10 million per month, the occupation of other parents and the ethnicity of students from Java. The highest forecasting results are found in the income variable of students' parents in cluster 3 with predictions of 1292 students in 2024. It is hoped that with clustering and forecasting based on this research, ITTelkom Surabaya can make the right decision as a basis for decision making to determine strategy in promoting the campus
Indonesian news classification application with named entity recognition approach
Full text linkNowadays, many netizens search for news via search engines with countless amounts of information, so it is increasingly difficult to determine when the number of news articles that appear changes very quickly and dynamically. Thus, it is necessary to process the extraction of news information to display the core information of the news. Problems arise, especially in Indonesian, which has a structure of various noun phrase entities with shallow parsing or grammatical induction. Named Entity Recognition (NER) has the opportunity to overcome this because it can extract news entities in depth, starting from proper nouns in text documents containing information search, machine translation, answering questions, and automatic summarization. This study aims to apply NER in Indonesian language news classification. This study uses Design-Based Research whose process includes (1) pre-implementation, (2) design, (3) implementation and revision, and finally, (4) reflection and evaluation. This application was developed on the platform python, streamlit, BeautifulSoup, gnews, and spacy library. The results of application accuracy testing have an F1-score value of 89.69% for all entities consisting of place, figure, day, date, and organization